© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 91576
    Prev
    Next
    INDEX
    Explanations

    fstab / fsc / fusha / fescues / fuser

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    0.79
     ల
    0.73
     아
    0.70
     источник
    0.67
     цей
    0.66
     οποία
    0.64
     artik
    0.63
    0.63
     દ
    0.63
     одна
    0.62
    POSITIVE LOGITS
     Edu
    0.72
     Blooms
    0.71
    ت
    0.69
    S
    0.66
    Edu
    0.66
    ע
    0.65
    socks
    0.65
    T
    0.65
    ිරීම
    0.64
     Și
    0.64
    Activations Density 0.001%

    No Known Activations